Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients

Ren, Zhimin; Sudderth, Erik B.

doi:10.1109/cvpr.2016.169

Cited by 140 publications

(111 citation statements)

References 26 publications

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…6D object pose estimators [27], [28], [29], [33] extract features from the input images (feature extraction block), and using the trained classifiers, estimate objects' 6D pose. Several methods further refine the output of the trained classifiers [104], [81], [149], [28], [29], [33] (refinement block), and finally hypothesise the object pose after filtering. Table II details the classification-based methods.…”

Section: A Classificationmentioning

confidence: 99%

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

Şahin

Garcia-Hernando

Sock

et al. 2020

Image and Vision Computing

View full text Add to dashboard Cite

Object pose recovery has gained increasing attention in the computer vision field as it has become an important problem in rapidly evolving technological areas related to autonomous driving, robotics, and augmented reality. Existing review-related studies have addressed the problem at visual level in 2D, going through the methods which produce 2D bounding boxes of objects of interest in RGB images. The 2D search space is enlarged either using the geometry information available in the 3D space along with RGB (Mono/Stereo) images, or utilizing depth data from LIDAR sensors and/or RGB-D cameras. 3D bounding box detectors, producing category-level amodal 3D bounding boxes, are evaluated on gravity aligned images, while full 6D object pose estimators are mostly tested at instance-level on the images where the alignment constraint is removed. Recently, 6D object pose estimation is tackled at the level of categories. In this paper, we present the first comprehensive and most recent review of the methods on object pose recovery, from 3D bounding box detectors to full 6D pose estimators. The methods mathematically model the problem as a classification, regression, classification & regression, template matching, and point-pair feature matching task. Based on this, a mathematical-model-based categorization of the methods is established. Datasets used for evaluating the methods are investigated with respect to the challenges, and evaluation metrics are studied. Quantitative results of experiments in the literature are analysed to show which category of methods best performs across what types of challenges. The analyses are further extended comparing two methods, which are our own implementations, so that the outcomes from the public results are further solidified. Current position of the field is summarized regarding object pose recovery, and possible research directions are identified.

show abstract

Section: A Classificationmentioning

confidence: 99%

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

Şahin

Garcia-Hernando

Sock

et al. 2020

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Although effective, 2D image-based methods ignore the spatial occupancy of objects, and can not fully exploit the depth information. While 3D volume-based methods usually convert the depth image into a volumetric representation, and exploit rich handcrafted 3D features [27,30] or learned 3D CNNs [31] for detecting 3D objects. Although existing methods can detect and segment visible 3D objects and scenes, they cannot infer the objects that are totally occluded.…”

Section: Related Workmentioning

confidence: 99%

Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion

Zhang

Liu

Lei

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Semantic Scene Completion (SSC) aims to simultaneously predict the volumetric occupancy and semantic category of a 3D scene. It helps intelligent devices to understand and interact with the surrounding scenes. Due to the high-memory requirement, current methods only produce low-resolution completion predictions, and generally lose the object details. Furthermore, they also ignore the multiscale spatial contexts, which play a vital role for the 3D inference. To address these issues, in this work we propose a novel deep learning framework, named Cascaded Context Pyramid Network (CCPNet), to jointly infer the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The proposed CCPNet improves the labeling coherence with a cascaded context pyramid. Meanwhile, based on the low-level features, it progressively restores the fine-structures of objects with Guided Residual Refinement (GRR) modules. Our proposed framework has three outstanding advantages: (1) it explicitly models the 3D spatial context for performance improvement; (2) full-resolution 3D volumes are produced with structure-preserving details;(3) light-weight models with low-memory requirements are captured with a good extensibility. Extensive experiments demonstrate that in spite of taking a single-view depth map, our proposed framework can generate high-quality SSC results, and outperforms state-of-the-art approaches on both the synthetic SUNCG and real NYU datasets.

show abstract

“…In addition, the cuboid fitting to the objects is performed as the minimal bounding cube of the 3D points, which is not the optimal solution when working with Kinect data, as discussed by (Jia et al, 2013). Recently, an interesting method that introduced the "Manhattan Voxel" was developed by (Ren and Sudderth, 2016). In their work the 3D layout of the room is estimated and detected objects are represented by 3D cuboids.…”

Section: Related Workmentioning

confidence: 99%

3D Reconstruction of Indoor Scenes using a Single RGB-D Image

Bokaris

Muselet

Trémeau

2017

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

To cite this version:Panagiotis-Alexandros Bokaris, Damien Muselet, Alain Trémeau. 3D reconstruction of indoor scenes using a single RGB-D image. 12th International Conference on Computer Vision Theory and Applications (VISAPP 2017), Feb 2017 3D reconstruction of indoor scenes using a single RGB-D image Abstract:The three-dimensional reconstruction of a scene is essential for the interpretation of an environment. In this paper, a novel and robust method for the 3D reconstruction of an indoor scene using a single RGB-D image is proposed. First, the layout of the scene is identified and then, a new approach for isolating the objects in the scene is presented. Its fundamental idea is the segmentation of the whole image in planar surfaces and the merging of the ones that belong to the same object. Finally, a cuboid is fitted to each segmented object by a new RANSAC-based technique. The method is applied to various scenes and is able to provide a meaningful interpretation of these scenes even in cases with strong clutter and occlusion. In addition, a new ground truth dataset, on which the proposed method is further tested, was created. The results imply that the present work outperforms recent state-of-the-art approaches not only in accuracy but also in robustness and time complexity.

show abstract

Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients

Cited by 140 publications

References 26 publications

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion

3D Reconstruction of Indoor Scenes using a Single RGB-D Image

Contact Info

Product

Resources

About